Training in progress, step 278, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e419c6b9165e42320f1a7472a3846377e8c91119c563d4005aff51a69aa4685
+oid sha256:d8cf8057910d23a062865985ba852f2938eae817046dfaf5681661132eaf58de
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28cdb21230b7824d55a4297c2ab3edbca84bc6dbaeedc644b7618d78672df3e0
+oid sha256:3538e3394b23b3adf8ac36f79431127cf553e2ff2786b3ddb23d8b296f28eeaa
 size 37431220

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70901b94b4e1e6b99201989f00c77c6a02ae46cc48fbef26b5bd41545d57275c
+oid sha256:c0786adcac2c7889cfa58c3afdb23ea4f83c558cdd0755806988521c514ef08d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7517146776406035,
+  "epoch": 0.7626886145404664,
   "eval_steps": 500,
-  "global_step": 274,
+  "global_step": 278,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1925,6 +1925,34 @@
       "learning_rate": 6.818181818181818e-05,
       "loss": 1.1167,
       "step": 274
+    },
+    {
+      "epoch": 0.7544581618655692,
+      "grad_norm": 0.15378378331661224,
+      "learning_rate": 6.742424242424242e-05,
+      "loss": 1.2406,
+      "step": 275
+    },
+    {
+      "epoch": 0.757201646090535,
+      "grad_norm": 0.16972492635250092,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 1.2506,
+      "step": 276
+    },
+    {
+      "epoch": 0.7599451303155007,
+      "grad_norm": 0.16112364828586578,
+      "learning_rate": 6.59090909090909e-05,
+      "loss": 1.1676,
+      "step": 277
+    },
+    {
+      "epoch": 0.7626886145404664,
+      "grad_norm": 0.1625635176897049,
+      "learning_rate": 6.515151515151516e-05,
+      "loss": 1.1607,
+      "step": 278
     }
   ],
   "logging_steps": 1,
@@ -1944,7 +1972,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.387494336322847e+17,
+  "total_flos": 3.438408126791516e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null